10 comments

  • florians 2 minutes ago
    What I want are precise and tight bounding boxes. Why is this so difficult?
  • icemaze 7 minutes ago
    Great in the benchmarks but not as good in the real world, sorry to say. Just gave it a try in my STT bot, it's worse than whisper
  • fraywing 9 minutes ago
    So is this basically a task-specific MoA transformer arch with a DNN that helps make routing decisions? Trying to understand this.
  • andai 30 minutes ago
    This is very cool, though I don't understand exactly what they've done here. Is it some kind of LLM with convolutional layers added?

    The graph doesn't exactly make it clear but it describes a pipeline that goes beyond the LLM, so the CNN could be a separate model there.

  • wood_spirit 2 hours ago
    > These are deep neural network architectures that are task-specific for things like OCR, translation, or GUI detection. The way they consume and see data is trained to be task specific, which makes them up to 100x more accurate at their specific task. They also produce useful metadata like bounding boxes and confidence scores, letting developers build predictable workflows they can rely on.

    Does code extraction and manipulation fit in that? Would interfaze be the agent that a coding agent uses?

    • yoeven 34 minutes ago
      Code extraction maybe, not something we have tested or built for but you could give it a try.

      Code manipulation probably not since it's a lot smaller of a model compared to a Claude Opus which is SOTA for code generation/manipulation.

      Generally code generation is a non-deterministic task by nature and general LLMs tend to be better at them.

      • wood_spirit 12 minutes ago
        The idea of what to change is perhaps an llm task but the job of doing the find replace and that kind of tooling is something LLMs actually struggle with and have all kinds or crutches and try retry loops to paste over in coding agents etc.
  • euroderf 1 hour ago
    Potentially stupid question: Does that mean we can chain them together line UNIX command line programs ? That would be so, so intuitive.
  • redwood 19 minutes ago
    Similar to a large action model?
  • sareiodata 2 hours ago
    Smaller models really arent great at structured output. If this works it would be great for a local model that might not be as good but as long as it respects structured output will be vastly more useful.
  • sweaterkokuro 2 hours ago
    This is cool, Id love to be able to fine tune on this architecture. Is this something on the roadmap ever?
    • yoeven 27 minutes ago
      It isn't on our roadmap right now since in most cases it should work out of the box and if it doesn't we'll work with you to train that into the model generally.

      However, if we see enough people who has something super niche that our model can't handle, we might start considering a fine tuning service

  • a7om_com 2 hours ago
    [flagged]